Making Few-Shot Object Detection Simpler and Less Frustrating

被引:1
作者
Bailer, Werner [1 ]
机构
[1] Joanneum Res, Graz, Austria
来源
MULTIMEDIA MODELING, MMM 2022, PT II | 2022年 / 13142卷
关键词
Few-shot learning; Object detection; Data preparation; Annotation tool; Incremental training;
D O I
10.1007/978-3-030-98355-0_37
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Few-shot object detection is useful in order to extend object detection capabilities in media production and archiving applications with specific object classes of interest for a particular organization or production context. While recent approaches for few-shot object detection have advanced the state of the art, they still do not fully meet the requirements of practical workflows, e.g., in media production and archiving. In these applications, annotated samples for novel classes are drawn from different data sources, they differ in numbers and it may be necessary to add a new class quickly to cover the requirements of a specific production. In contrast, current frameworks for few-shot object detection typically assume a static dataset, which is split into the base and novel classes. We propose a toolchain to facilitate training for fewshot object detection, which takes care of data preparation when using heterogeneous training data and setup of training steps. The toolchain also creates annotation files to use combined data sets as new base models, which facilitates class-incremental training. We also integrated the toolchain with an annotation UI.
引用
收藏
页码:445 / 451
页数:7
相关论文
共 6 条
  • [1] Incremental Few-Shot Instance Segmentation
    Ganea, Dan Andrei
    Boom, Bas
    Poppe, Ronald
    [J]. 2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, : 1185 - 1194
  • [2] Few-shot Object Detection via Feature Reweighting
    Kang, Bingyi
    Liu, Zhuang
    Wang, Xin
    Yu, Fisher
    Feng, Jiashi
    Darrell, Trevor
    [J]. 2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 8419 - 8428
  • [3] RepMet: Representative-based metric learning for classification and few-shot object detection
    Karlinsky, Leonid
    Shtok, Joseph
    Harary, Sivan
    Schwartz, Eli
    Aides, Amit
    Feris, Rogerio
    Giryes, Raja
    Bronstein, Alex M.
    [J]. 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, : 5192 - 5201
  • [4] Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
    Ren, Shaoqing
    He, Kaiming
    Girshick, Ross
    Sun, Jian
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (06) : 1137 - 1149
  • [5] R-FCN-3000 at 30fps: Decoupling Detection and Classification
    Singh, Bharat
    Li, Hengduo
    Sharma, Abhishek
    Davis, Larry S.
    [J]. 2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 1081 - 1090
  • [6] Wang X., 2020, P 37 INT C MACHINE L, P9919